Object Detection with Neural Models, Deep Learning and Common Sense to Aid Smart Mobility
The advent of autonomous transportation systems is attracting attention in AI today. Despite how far this area has progressed, there are situations better handled by humans. One of these is distinguishing objects seen for the first time and making decisions accordingly. Hence, our focus in this paper is on object detection, which can potentially enhance autonomous driving and other types of automation in transportation systems. This impacts Smart Mobility in Smart Cities. We provide expanded analysis of recent object detection techniques including neural models, deep learning and related advances. We highlight a novel object detection system called YOLO (You Only Look Once) and conduct its performance evaluation on real-time data. We point out challenges in this field and then explore the use of Commonsense Knowledge (CSK) in object detection with neural models and deep learning, emphasizing the importance of CSK to capture intuitive human reasoning. We explain how this work would potentially enhance autonomous vehicles and transportation systems. This work thus constitutes an exploratory paper that embodies a vision in Smart Mobility.
Montclair State University Digital Commons Citation
Pandey, Abidha; Puri, Manish; and Varde, Aparna, "Object Detection with Neural Models, Deep Learning and Common Sense to Aid Smart Mobility" (2018). Department of Computer Science Faculty Scholarship and Creative Works. 431.